R
Rahul Baburajan
Researcher at International Institute of Information Technology, Hyderabad
Publications - 4
Citations - 66
Rahul Baburajan is an academic researcher from International Institute of Information Technology, Hyderabad. The author has contributed to research in topics: Fourier transform & Inverse problem. The author has an hindex of 3, co-authored 4 publications receiving 60 citations.
Papers
More filters
Journal ArticleDOI
Solving Inverse Computational Imaging Problems Using Deep Pixel-Level Prior
TL;DR: In this article, an autoregressive model is proposed to learn a deep generative model once and then use it as a signal prior for solving various inverse problems in computational imaging.
Posted Content
Phase retrieval for Fourier Ptychography under varying amount of measurements
TL;DR: In this paper, an auto-encoder based architecture is proposed for phase retrieval under both low overlap, where traditional techniques completely fail, and at higher levels of overlap, and for the high overlap case, optimizing the generator for reducing the forward model error is an appropriate choice.
Proceedings Article
Phase retrieval for Fourier Ptychography under varying amount of measurements.
TL;DR: In this paper, an auto-encoder based architecture is proposed for phase retrieval under both low overlap, where traditional techniques completely fail, and at higher levels of overlap, and for the high overlap case, optimizing the generator for reducing the forward model error is an appropriate choice.
Posted Content
Solving Inverse Computational Imaging Problems using Deep Pixel-level Prior
TL;DR: This paper shows that among the various state-of-the-art deep generative models, autoregressive models are especially suitable for this purpose for the following reasons: first, they explicitly model the pixel level dependencies and hence are capable of reconstructing low-level details better, and second, they provide an explicit expression for the image prior, which can be used for MAP-based inference along with the forward model.